diff --git a/ocrmypdf/pageinfo.py b/ocrmypdf/pageinfo.py
index 1984511a..92c01faa 100644
--- a/ocrmypdf/pageinfo.py
+++ b/ocrmypdf/pageinfo.py
@@ -98,6 +98,22 @@ InlineSettings = namedtuple('InlineSettings',
 ContentsInfo = namedtuple('ContentsInfo', ['raster_settings', 'inline_images'])
 
 
+def _normalize_stack(operations):
+    """Fix runs of qQ's in the stack
+
+    For some reason PyPDF2 converts runs of qqq, QQ, QQQq, etc. into single
+    operations.  Break this silliness up and issue each stack operation
+    individually so we don't lose count.
+
+    """
+    for operands, command in operations:
+        if re.match(br'Q*q+$', command):   # Zero or more Q, one or more q
+            for char in command:           # Split into individual bytes
+                yield ([], bytes([char]))  # Yield individual bytes
+        else:
+            yield (operands, command)
+
+
 def _interpret_contents(contentstream):
     """Interpret the PDF content stream
 
@@ -127,14 +143,19 @@ def _interpret_contents(contentstream):
     image_raster_settings = []
     inline_images = []
 
-    for op in operations:
+    for n, op in enumerate(_normalize_stack(operations)):
         operands, command = op
         if command == b'q':
             stack.append(ctm)
             if len(stack) > 32:
-                raise RuntimeError("PDF graphics stack overflow")
+                raise RuntimeError(
+                    "PDF graphics stack overflow, command %i" % n)
         elif command == b'Q':
-            ctm = stack.pop()
+            try:
+                ctm = stack.pop()
+            except IndexError:
+                raise RuntimeError(
+                    "PDF graphics stack underflow, command %i" % n)
         elif command == b'cm':
             ctm = matrix_mult(
                 _matrix_from_shorthand(operands), ctm)
diff --git a/tests/resources/README.rst b/tests/resources/README.rst
index a8f29346..fd515361 100644
--- a/tests/resources/README.rst
+++ b/tests/resources/README.rst
@@ -79,6 +79,9 @@ under the terms of the license in LICENSE.rst.
     *   - missing_docinfo.pdf
         - @jbarlow83
         - PDF file with no /DocumentInfo section 
+    *   - overlay.pdf
+        - @maxandersen
+        - PDF file generated by PDFPen pro that triggered content stream parse errors
 
 Assemblies
 ==========
diff --git a/tests/resources/overlay.pdf b/tests/resources/overlay.pdf
new file mode 100644
index 00000000..f8a29dbd
Binary files /dev/null and b/tests/resources/overlay.pdf differ
diff --git a/tests/test_main.py b/tests/test_main.py
index 3bced8d9..0abfc392 100644
--- a/tests/test_main.py
+++ b/tests/test_main.py
@@ -687,3 +687,8 @@ def test_very_high_dpi(spoof_tesseract_cache, resources, outpdf):
     "Checks for a Decimal quantize error with high DPI, etc"
     check_ocrmypdf(resources / '2400dpi.pdf', outpdf,
                    env=spoof_tesseract_cache)
+
+
+def test_overlay(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'overlay.pdf', outpdf,
+                   env=spoof_tesseract_noop)